Abstract: With the rapid development of synthetic aperture radar (SAR) satellites and their application technology in the ocean field, there is an urgent need to develop application-oriented fast automatic detection and feature inversion methods for marine internal waves on-board satellites to solve the contradiction between massive satellite data and rapid applications. On the basis of analyzing the characteristics of ocean SAR images, a method combining image power spectrum features with improved elliptical domain normalized Radon transform is proposed to automatically detect the ocean region containing internal waves. While locating the internal wave region, the wavelength, direction, and velocity parameters of the internal waves in the region are inverted. The experimental results show that the method combining image power spectrum features with improved elliptical domain normalized Radon transform can automatically detect the ocean internal wave region in SAR images and quickly invert the internal wave wavelength, direction, and velocity. It has the advantages of high automation, high detection rate, and low false alarm rate, and can provide an important reference for the automatic detection and feature inversion of ocean internal waves in SAR images.